The official implementation of Time-aware Personalized Graph Convolutional Network for Multivariate Time Series Forecasting

The official implementation of SDGL

Predict stock with LSTM supporting pytorch, keras and tensorflow

Official implementation of our ICLR 2023 paper "Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting"

🍀 Pytorch implementation of various Attention Mechanisms, MLP, Re-parameter, Convolution, which is helpful to further understand papers.⭐⭐⭐

基于LSTM的时间序列预测研究

An Open Source Standard Time Series Forecasting Benchmark.

Code for our CIKM'22 short paper Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting.

Data Science Using Python

Pytorch🍊🍉 is delicious, just eat it! 😋😋

PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Models (CIKM 2021)

An index of recommendation algorithms that are based on Graph Neural Networks.

Must-read papers on graph neural networks (GNN)

Some GNNs are implemented using PyG for node classification tasks, including: GCN, GraphSAGE, SGC, GAT, R-GCN and HAN (Heterogeneous Graph Attention Network), which will continue to be updated in t…

DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting, which is accepted at ICML2022.

The Unified Machine Learning Framework

MTGNN review & codes.

PyTorch Implementation and Explanation of Graph Representation Learning papers: DeepWalk, GCN, GraphSAGE, ChebNet & GAT.

🎨 ML Visuals contains figures and templates which you can reuse and customize to improve your scientific writing.

Tutorial about Graph Convolutional Network(GCN)

An adversarial example library for constructing attacks, building defenses, and benchmarking both

《深入浅出图神经网络：GNN原理解析》配套代码

A comprehensive collection of recent papers on graph deep learning

TPAMI 2022

Implementation of Convolutional LSTM in PyTorch.

This is the PyTorch implementation of TPA-LSTM

Deep InfoMax (DIM), or "Learning Deep Representations by Mutual Information Estimation and Maximization"